Three-dimensional target detection method and device based on multi-sensor information fusion

Abstract

The invention discloses a three-dimensional target detection method, apparatus and device based on multi-sensor information fusion, and a computer readable storage medium. The three-dimensional targetdetection method comprises the steps: fusing 3D point cloud and an RGB image collected by a laser radar and a camera sensor, and generating an RGB-I image; generating a multi-channel aerial view according to the 3D point cloud so as to determine a region of interest; respectively extracting and fusing region-of-interest features of the RGB-I image and the aerial view based on a convolutional neural network; utilizing a multi-layer perceptron to fuse the confidence coefficient, the approximate position and the size of the image prediction target based on the features of the region of interest,and determining a candidate box; adaptively endowing different pixel weights to different sensor candidate box feature maps based on an attention mechanism, and carrying out skip fusion; and processing the candidate frame feature fusion image by using a multi-layer perceptron, and outputting a three-dimensional detection result. According to the three-dimensional target detection method, apparatus and device, and the computer readable storage medium provided by the invention, the target recognition rate is improved, and the target can be accurately positioned.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a three-dimensional target detection method, device, equipment and computer-readable storage medium based on multi-sensor information fusion. Background technique [0002] The automatic driving technology with prevention and intelligence as the core has become an urgent need of modern transportation. Solving the multi-target recognition and 3D positioning of smart vehicles in complex scenes is the key to 3D environment perception and the prerequisite for safe and reliable driving of vehicles. It is difficult for a traditional single sensor to identify and detect dynamic or static targets in a scene in a timely and accurate manner. Multi-sensor joint detection and complementary advantages are the trend of intelligent perception. At present, the multi-sensor-based 3D target detection technology still has insufficient initial feature extraction of source data; mult...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a three-dimensional target detection method, device, equipment and computer-readable storage medium based on multi-sensor information fusion to solve the problem of rough and inefficient multi-modal data matching and fusion in the prior art and three-dimensional targets in complex environments Problems that cannot be precisely identified and located

Images